We have 10 of 44 papers
We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.
Not the right person? Other researchers publish under this name.
The ARIA framework for MAS-agnostic runtime inspection and amendment is developed, designed to integrate with any MAS that exposes execution trajectories and supports continuation replacement, and a compact model is taught to recognize when intervention is needed and how to correct an ongoing run.
LLM agents increasingly operate over multiple entities, where reliable response generation requires not only retrieving relevant evidence but also preserving its association with the correct entity. We identify Phantom Merge (PM), an entity-evidence binding failure in which an agent attributes unsupported claims to its...
MolP2SBench is introduced, a benchmark for molecular property-to-structure (P2S) reasoning in LLMs that supports studying how LLMs extract and use physical-property information, revealing patterns that may differ from conventional chemical intuition and providing a foundation for more reliably property-grounded models...
Large language models (LLMs) deployed through text-only APIs face model extraction risks, as adversaries can collect their responses to train surrogates that reproduce their capabilities. While prior work has developed diverse attacks and defenses, evaluations remain fragmented across access assumptions, model configur...
LLM compression reduces inference costs and memory requirements, but selecting a method and configuration remains largely empirical because comparable resource reductions can produce different capability losses. We systematically investigate capability scaling-down laws for LLM compression across pruning, quantization,...
Understanding and assessing natural hazards is essential for disaster preparedness and risk reduction. Recent advances in large language models have spurred growing interest in AI agents for hazard analysis, particularly their ability to integrate scientific data, models, and tools into automated workflows. However, ef...
How much does the noisy measurement add to learned quantum error mitigation? An accuracy table cannot say, because a model handed circuit structure can score well without reading the measurement at all. QEMScore adds the comparison that can. Each simulated circuit carries an exact ideal answer. The learned mitigator is...
Experiments show that Knowledge Trap reduces surrogate Agreement by 6.2\% on average without degrading legitimate-user accuracy, outperforming existing defenses that impose measurable user impact, and suggest that defending knowledge-space traversal is a practical direction for mitigating LLM extraction attacks.
This work forms model extraction monitoring as benign-calibrated traffic-window distribution testing: embed incoming queries into a semantic space and test whether their aggregate distribution deviates from historical benign traffic.
TIGER is presented, an inference-time framework that redesigns feedback for localized repair that reduces unsupported content while preserving task quality and a CrisisFACTS case study suggests that the same repair mechanism can improve grounding in multi-source settings.
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.
